Part II - Ford GoBike System Dataset

by Saoban Lateefat

Investigation Overview

In this analysis, I looked into :
What gender rides the bikes the most
The average duration of each rides
Age range of people who takes the ride
The hour of the day people takes rides the most . and so on..

Dataset Overview

The dataset consists of 183412 rows and 16 columns of different datatypes.

# import all packages and set plots to be embedded inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px


%matplotlib inline

# suppress warnings from final output
import warnings
warnings.simplefilter("ignore")

bike = pd.read_csv('201902-fordgobike-tripdata.csv')

#Date wrangling, fixing null values
bike['member_birth_year'].fillna(bike['member_birth_year'].mode()[0], inplace = True)
bike['member_gender'].fillna(bike['member_gender'].mode()[0], inplace = True)
bike.dropna(inplace = True)
#bike.isnull().sum()

# Changing the datatypes to the appropraite ones
bike['start_time'] = pd.to_datetime(bike['start_time'], format= '%Y-%m-%d %H:%M:%S')
bike['end_time'] = pd.to_datetime(bike['end_time'], format= '%Y-%m-%d %H:%M:%S')

bike['member_birth_year'] = bike['member_birth_year'].astype(int)

# Copy the data
bike_clean = bike.copy()

#Generating another columns
bike_clean['start_weekday_name'] = bike_clean['start_time'].dt.day_name()
bike_clean['end_weekday_name'] = bike_clean['end_time'].dt.day_name()
bike_clean['hh'] = bike_clean['start_time'].dt.strftime('%H')
bike_clean['member_age'] = (2019 - bike_clean['member_birth_year'])
bike_clean['member_age']

0         35
1         31
2         47
3         30
4         45
          ..
183407    23
183408    35
183409    29
183410    31
183411    30
Name: member_age, Length: 183215, dtype: int32

Trip per User type, Gender and Age

-- There are more of people who are subscribers to customers
-- We have more males to female
-- We have younger people who board bikes to older people

count = bike_clean['user_type'].value_counts()
label = ['Subscriber', 'Customer']
colors = ["#8c564b", "#ff7f0e"]
fig = plt.figure(figsize =(10, 7))
plt.pie(count, labels = label, autopct='%1.1f%%', colors=colors)
plt.title("User Type ")
 
# show plot
plt.show()

base_color = sns.color_palette()[0]
plt.title("Count per gender ")
gender = bike_clean['member_gender'].value_counts().index
sns.countplot(data=bike_clean, y='member_gender', color=base_color, order=gender);

fig = px.histogram(bike_clean, x = 'member_age', title = 'Age per rides')
fig.show()

Trips per weekday and hour of the day

-- We have higher trips on weekdays to weekends
-- Most ofthe trip is made around 5pm and 8am and we deduce this is due to rush hours.

weekdays = ['Sunday', 'Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday']
fig, ax = plt.subplots(nrows=2, figsize = [8,8])

#plt.title = 'Rides per weekdays'
default_color = sns.color_palette()[0]
sns.countplot(data = bike_clean, x = 'start_weekday_name', color = default_color, ax = ax[0], order = weekdays).set(title = 'Rides per weekdays')
sns.countplot(data = bike_clean, x = 'end_weekday_name', color = default_color, order = weekdays)

plt.show()

plt.figure(figsize = [15, 10]);
base_color = sns.color_palette()[0]
plt.title("Count per hour ")
hour = bike_clean['hh'].value_counts().index
sns.countplot(data=bike_clean, y='hh', color = base_color, order=hour);

!jupyter nbconvert Project_three_II.ipynb --to slides --post serve --no-input --no-prompt

[NbConvertApp] Converting notebook Project_three_II.ipynb to slides
[NbConvertApp] Writing 4799212 bytes to Project_three_II.slides.html
[NbConvertApp] Redirecting reveal.js requests to https://cdnjs.cloudflare.com/ajax/libs/reveal.js/3.5.0
Traceback (most recent call last):
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\Scripts\jupyter-nbconvert-script.py", line 10, in <module>
    sys.exit(main())
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\jupyter_core\application.py", line 254, in launch_instance
    return super(JupyterApp, cls).launch_instance(argv=argv, **kwargs)
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\traitlets\config\application.py", line 845, in launch_instance
    app.start()
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\nbconvert\nbconvertapp.py", line 350, in start
    self.convert_notebooks()
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\nbconvert\nbconvertapp.py", line 524, in convert_notebooks
    self.convert_single_notebook(notebook_filename)
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\nbconvert\nbconvertapp.py", line 491, in convert_single_notebook
    self.postprocess_single_notebook(write_results)
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\nbconvert\nbconvertapp.py", line 463, in postprocess_single_notebook
    self.postprocessor(write_results)
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\nbconvert\postprocessors\base.py", line 28, in __call__
    self.postprocess(input)
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\nbconvert\postprocessors\serve.py", line 90, in postprocess
    http_server.listen(self.port, address=self.ip)
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\tornado\tcpserver.py", line 151, in listen
    sockets = bind_sockets(port, address=address)
  File "C:\Users\SAOBAN\Documents\Saoban_Anaconda\lib\site-packages\tornado\netutil.py", line 161, in bind_sockets
    sock.bind(sockaddr)
OSError: [WinError 10048] Only one usage of each socket address (protocol/network address/port) is normally permitted